INDEX

Explanations

places or locations, specifically focusing on the city of Rome

oai_token-act-pair · gpt-3.5-turbo

mentions of the city of Rome

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intosh

-1.09

Marginal

-0.92

TPPStreamerBot

-0.86

lasses

-0.86

merce

-0.85

lished

-0.78

innon

-0.77

ramid

-0.76

aminer

-0.75

rity

-0.75

POSITIVE LOGITS

 Pact

0.86

 Inquisition

0.79

 Reign

0.78

 Cathedral

0.76

 Catholicism

0.75

 cathedral

0.75

 Cardinal

0.72

 Cell

0.71

 Archbishop

0.69

 Statue

0.69

Activations Density 0.007%

places or locations, specifically focusing on the city of Rome

mentions of the city of Rome

No Comments

No Known Activations